Education, University and Research

USES: when mental health comes through social media

06 May 2024

Curated by Sarah Peregalli

Can a tweet or an Instagram post tell us anything about our mental health? How important is the relationship between well-being and the use of these platforms? To answer these questions Marta Fadda, researcher in bioethics at USI, Oliver Grübner, health geographer, and Marcus Wolf, psychologist, both from the University of Zurich, conducted a series of studies to demonstrate the usefulness of social platforms for research in the field of mental health. The team of three researchers won the first edition of the UZH Postdoc Team Award. The objective of this interdisciplinary research is to investigate the links between social media posts and the mental health of the population. Dr. Marta Fadda tells us about it

What does the research relating to this aspect of mental health consist of? What tools does he use?

«The research consists of the analysis of a vast quantity of tweets, for which the geographic location of the user was available at the time of sharing, using innovative emotion recognition tools. As you might imagine, extracting, preserving, analyzing and sharing the data and results of the various studies we have conducted has important ethical and legal implications. For example, users do not provide informed consent for the analysis of their tweets for specific research purposes as is typically the case in other studies, and the preservation of these tweets could expose users to privacy risks. Personally, I was responsible for analyzing the ethical and legal issues related to the various studies we carried out, and coordinating the team in identifying and implementing ethically and legally justifiable solutions. In short, I asked myself whether it was ethical and legal to put into practice the technologies we had available to answer our research questions with the type of data collected."

How can you determine a person's mental health from what they write on social media?

«Our emotions are indicators of our mental health. The analysis we used consists of using a software called EMOTIVE which detects and measures emotions in posts on social platforms. This software extracts eight emotions: anger, disgust, fear, happiness, sadness, surprise, shame and confusion. Studying the distribution of these emotions over time and space provides valuable information regarding how groups of people react to certain events."

What practical implications does this research have in the area?

“For example, Dr. Grübner found that the negative emotional reactions identified in tweets from those in New York during and after Hurricane Sandy were concentrated in specific neighborhoods of the city, particularly Staten Island. This information allows us to plan and implement targeted interventions to deal with emergencies where they affect the most."

The fact that we have cutting-edge technologies available today does not necessarily mean that their use is ethical or legal. What are the ethical and legal implications of these studies?

«The fact that people freely share their opinions, experiences and emotions on social platforms does not mean that researchers (or others) can take possession of this information and make any use they choose. Users who generate content online, even on completely open platforms that can be consulted by anyone, have rights regarding their privacy that must be respected. Imagine walking down a supermarket aisle with your shopping cart. While on the one hand you can expect to meet people, and that they can take a look at what you probably intend to buy, on the other hand you would probably be annoyed to discover that someone has followed you from the moment you entered to the exit, and that he had recorded all your movements, your purchases, and your exchanges with the sales staff. Furthermore, the analysis of large quantities of posts, if not conducted in a scientifically robust way, can generate erroneous conclusions which can lead to the spread of stereotypes and negative judgments among the population."

How did you deal with these problems?

«The ethics and legality of our studies have always been in first place. In addition to discussing with each other within the team, we consulted the scientific literature that addressed the ethical and legal challenges of similar studies, and we interfaced with various institutions including data protection authorities at national level. cantonal. However, we realized that the available guidelines did not take into account a unique aspect of our data: the geographic location of the collected posts. We have thus developed new guidelines in an interdisciplinary manner that take this further aspect into account. For example, there are very important privacy issues if we consider that the tweet we analyze contains the exact location of the person at the time the tweet was shared. One of our recommendations was to modify the geographical position data and extend it to a larger area so as to further limit the possibility of precisely locating the person."

Source: Fadda M, Sykora M, Elayan S, Puhan MA, Naslund JA, Mooney SJ, Albanese E, Morese R, Gruebner O. Ethical issues of collecting, storing, and analyzing geo-referenced tweets for mental health research. Digi Health. 2022 Apr 12;8:20552076221092539. doi: 10.1177/20552076221092539. PMID: 35433020; PMCID: PMC9008807. (https://pubmed.ncbi.nlm.nih.gov/35433020/)